Nature Will 发布首个物理世界基础模型 Natura-1
Nature Will 发布了首个面向物理世界的基础模型 Natura-1，该模型基于 100 万小时人类第一视角视频训练，支持对物体位置和朝向的细粒度指令。Natura-1 具备双手协同操作能力，能在抓取方式变化时保持控制，并可在长任务中跟踪物体状态以规划后续动作。
🚨 AI News | TestingCatalog· @testingcatalog · X·2026-10-13 19:03· 25 分钟前AI 评分50
AI 导读
Nature Will 发布其首个面向物理世界的基础模型 Natura-1，训练数据为 100 万小时人类处理不同场景与物体的第一视角视频，可处理从未见过的物体和任务。模型支持指定物体最终位置和朝向的细粒度指令，能在抓取方式中途变化时保持控制、双手执行不同任务，并可在长任务中跟踪已移动或打开的物体以确定下一步。
正文
Nature Will @naturewill has launched Natura-1, its first foundation model for the physical world!
Natura-1 is trained on one million hours of egocentric video data of humans handling different scenarios and objects, enabling it to handle objects and tasks it has never seen before.
The model allows instructions to get specific, down to where an object should end up and which way it should face.
It can maintain control as its grip shifts mid-task, and do different tasks with each hand.
On longer tasks, Natura-1 can track what it has already moved or opened and determine the next step. https://x.com/naturewill/status/2109858475333570565/video/1
来源：🚨 AI News | TestingCatalog · x.com
来源：AIHot · aihot.news